Skip to main content

← Dracon Bench leaderboard

nemotron-3-nano-omni-30b-a3b-reasoning:free vs flint-v1.0:free

Scores

Suitenemotron-3-nano-omni-30b-a3b-reasoning:freeflint-v1.0:freeDelta
IFEval-50 prompt89.8%93.3%-3.5 pts
GSM8K-5078.0%88.1%-10.1 pts
SVG total104/250144/250-40

beach 17 vs 31

Sun low over water with a reflection path; distant objects smaller and hazier than near ones.

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

17/50

recursive/flint-v1.0:free

31/50

clock 31 vs 37

A clock is checkable to the minute: 10:10 means the hour hand just past 10, the minute hand on 2.

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

31/50

12 1 2 3 4 5 6 7 8 9 10 11 DRACON

recursive/flint-v1.0:free

37/50

12 1 2 3 4 5 6 7 8 9 10 11 DRACON

duo 20 vs 26

Two characters mid-action, not posed: a dog driving a jet ski, a raccoon holding on.

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

20/50

recursive/flint-v1.0:free

26/50

monalisa 16 vs 26

Leonardo's portrait: three-quarter bust, folded hands, winding river landscape behind.

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

16/50

recursive/flint-v1.0:free

26/50

pelican 20 vs 24

Everyone knows what a pelican looks like: large beak with throat pouch, long neck, webbed feet.

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

20/50

recursive/flint-v1.0:free

24/50